Updated patches to work with the current trunk.

[rsync/rsync-patches.git] / sparse-block.diff

This patch adds the --sparse-block option.  Andrea Righi writes:

  In some filesystems, typically optimized for large I/O throughputs (like
  IBM GPFS, IBM SAN FS, or distributed filesystems in general) a lot of
  lseek() operations can strongly impact on performances. In this cases it
  can be helpful to enlarge the block size used to handle sparse files
  directly from a command line parameter.

  For example, using a sparse write size of 32KB, I've been able to
  increase the transfer rate of an order of magnitude copying the output
  files of scientific applications from GPFS to GPFS or GPFS to SAN FS.

  -Andrea

To use this patch, run these commands for a successful build:

    patch -p1 <patches/sparse-block.diff
    ./configure                               (optional if already run)
    make

diff --git a/fileio.c b/fileio.c
index 0faa619..b76dc02 100644
--- a/fileio.c
+++ b/fileio.c
@@ -27,6 +27,7 @@
 #endif
 
 extern int sparse_files;
+extern int sparse_files_block_size;
 
 static char last_byte;
 static OFF_T sparse_seek = 0;
@@ -116,7 +117,7 @@ int write_file(int f, char *buf, int len)
 	while (len > 0) {
 		int r1;
 		if (sparse_files > 0) {
-			int len1 = MIN(len, SPARSE_WRITE_SIZE);
+			int len1 = MIN(len, sparse_files_block_size);
 			r1 = write_sparse(f, buf, len1);
 		} else {
 			if (!wf_writeBuf) {
diff --git a/options.c b/options.c
index e7c6c61..a0fb2e7 100644
--- a/options.c
+++ b/options.c
@@ -73,6 +73,7 @@ int remove_source_files = 0;
 int one_file_system = 0;
 int protocol_version = PROTOCOL_VERSION;
 int sparse_files = 0;
+long sparse_files_block_size = SPARSE_WRITE_SIZE;
 int do_compression = 0;
 int def_compress_level = Z_DEFAULT_COMPRESSION;
 int am_root = 0; /* 0 = normal, 1 = root, 2 = --super, -1 = --fake-super */
@@ -703,6 +704,7 @@ void usage(enum logcode F)
   rprintf(F,"     --fake-super            store/recover privileged attrs using xattrs\n");
 #endif
   rprintf(F," -S, --sparse                handle sparse files efficiently\n");
+  rprintf(F,"     --sparse-block=SIZE     set the block size used to handle sparse files\n");
   rprintf(F," -n, --dry-run               perform a trial run with no changes made\n");
   rprintf(F," -W, --whole-file            copy files whole (without delta-xfer algorithm)\n");
   rprintf(F," -x, --one-file-system       don't cross filesystem boundaries\n");
@@ -899,6 +901,7 @@ static struct poptOption long_options[] = {
   {"sparse",          'S', POPT_ARG_VAL,    &sparse_files, 1, 0, 0 },
   {"no-sparse",        0,  POPT_ARG_VAL,    &sparse_files, 0, 0, 0 },
   {"no-S",             0,  POPT_ARG_VAL,    &sparse_files, 0, 0, 0 },
+  {"sparse-block",     0,  POPT_ARG_LONG,   &sparse_files_block_size, 0, 0, 0 },
   {"inplace",          0,  POPT_ARG_VAL,    &inplace, 1, 0, 0 },
   {"no-inplace",       0,  POPT_ARG_VAL,    &inplace, 0, 0, 0 },
   {"append",           0,  POPT_ARG_NONE,   0, OPT_APPEND, 0, 0 },
@@ -2416,6 +2419,12 @@ void server_options(char **args, int *argc_p)
 		args[ac++] = arg;
 	}
 
+	if (sparse_files_block_size) {
+		if (asprintf(&arg, "--sparse-block=%lu", sparse_files_block_size) < 0)
+			goto oom;
+		args[ac++] = arg;
+	}
+
 	if (io_timeout) {
 		if (asprintf(&arg, "--timeout=%d", io_timeout) < 0)
 			goto oom;
diff --git a/rsync.yo b/rsync.yo
index 941f7a5..5fa8396 100644
--- a/rsync.yo
+++ b/rsync.yo
@@ -359,6 +359,7 @@ to the detailed description below for a complete description.  verb(
      --super                 receiver attempts super-user activities
      --fake-super            store/recover privileged attrs using xattrs
  -S, --sparse                handle sparse files efficiently
+     --sparse-block=SIZE     set block size used to handle sparse files
  -n, --dry-run               perform a trial run with no changes made
  -W, --whole-file            copy files whole (w/o delta-xfer algorithm)
  -x, --one-file-system       don't cross filesystem boundaries
@@ -1120,6 +1121,15 @@ NOTE: Don't use this option when the destination is a Solaris "tmpfs"
 filesystem. It doesn't seem to handle seeks over null regions
 correctly and ends up corrupting the files.
 
+dit(bf(--sparse-block=SIZE)) Change the block size used to handle sparse files
+to SIZE bytes.  This option only has an effect if the bf(--sparse) (bf(-S))
+option was also specified.  The default block size used by rsync to detect a
+file hole is 1024 bytes; when the receiver writes data to the destination file
+and option bf(--sparse) is used, rsync checks every 1024-bytes chunk to detect
+if they are actually filled with data or not.  With certain filesystems,
+optimized to receive data streams for example, enlarging this block size can
+strongly increase performance.  The option can be used to tune this block size.
+
 dit(bf(-n, --dry-run)) This makes rsync perform a trial run that doesn't
 make any changes (and produces mostly the same output as a real run).  It
 is most commonly used in combination with the bf(-v, --verbose) and/or